Unipa-GPT: Large Language Models for university-oriented QA in Italian

This paper illustrates the architecture and training of Unipa-GPT, a chatbot relying on a Large Language Model, developed for assisting students in choosing a bachelor/master degree course at the University of Palermo. Unipa-GPT relies on gpt-3.5-turbo, it was presented in the context of the Europea...

Full description

Saved in:
Bibliographic Details
Main Authors: Irene Siragusa, Roberto Pirrone
Format: Article
Language:English
Published: Accademia University Press 2024-12-01
Series:IJCoL
Online Access:https://journals.openedition.org/ijcol/1476
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849683400504377344
author Irene Siragusa
Roberto Pirrone
author_facet Irene Siragusa
Roberto Pirrone
author_sort Irene Siragusa
collection DOAJ
description This paper illustrates the architecture and training of Unipa-GPT, a chatbot relying on a Large Language Model, developed for assisting students in choosing a bachelor/master degree course at the University of Palermo. Unipa-GPT relies on gpt-3.5-turbo, it was presented in the context of the European Researchers’ Night (SHARPER night). In our experiments we adopted both the Retrieval Augmented Generation (RAG) approach and fine-tuning to develop the system. The whole architecture of Unipa-GPT is presented, both the RAG and the fine-tuned systems are compared, and a brief discussion on their performance is reported. Further comparison with other Large Language Models and the experimental results during the SHARPER night are illustrated. Corpora and code are available on GitHub1.
format Article
id doaj-art-cddcfcf52d2047ce9d3f55e92a346f88
institution DOAJ
issn 2499-4553
language English
publishDate 2024-12-01
publisher Accademia University Press
record_format Article
series IJCoL
spelling doaj-art-cddcfcf52d2047ce9d3f55e92a346f882025-08-20T03:23:52ZengAccademia University PressIJCoL2499-45532024-12-01102Unipa-GPT: Large Language Models for university-oriented QA in ItalianIrene SiragusaRoberto PirroneThis paper illustrates the architecture and training of Unipa-GPT, a chatbot relying on a Large Language Model, developed for assisting students in choosing a bachelor/master degree course at the University of Palermo. Unipa-GPT relies on gpt-3.5-turbo, it was presented in the context of the European Researchers’ Night (SHARPER night). In our experiments we adopted both the Retrieval Augmented Generation (RAG) approach and fine-tuning to develop the system. The whole architecture of Unipa-GPT is presented, both the RAG and the fine-tuned systems are compared, and a brief discussion on their performance is reported. Further comparison with other Large Language Models and the experimental results during the SHARPER night are illustrated. Corpora and code are available on GitHub1.https://journals.openedition.org/ijcol/1476
spellingShingle Irene Siragusa
Roberto Pirrone
Unipa-GPT: Large Language Models for university-oriented QA in Italian
IJCoL
title Unipa-GPT: Large Language Models for university-oriented QA in Italian
title_full Unipa-GPT: Large Language Models for university-oriented QA in Italian
title_fullStr Unipa-GPT: Large Language Models for university-oriented QA in Italian
title_full_unstemmed Unipa-GPT: Large Language Models for university-oriented QA in Italian
title_short Unipa-GPT: Large Language Models for university-oriented QA in Italian
title_sort unipa gpt large language models for university oriented qa in italian
url https://journals.openedition.org/ijcol/1476
work_keys_str_mv AT irenesiragusa unipagptlargelanguagemodelsforuniversityorientedqainitalian
AT robertopirrone unipagptlargelanguagemodelsforuniversityorientedqainitalian